Search Packages

vosk

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

speechmatics-rt

Python SDKs for Speechmatics APIs

speechmatics-voice

Python SDKs for Speechmatics APIs

khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

khoj-assistant

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

speechmatics-batch

Python SDKs for Speechmatics APIs

vision-agents

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

moonshine-voice

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

onnx-asr

A lightweight Python package for Automatic Speech Recognition using ONNX models

werpy

🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.

stt

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

vision-agents-plugins-getstream

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-deepgram

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-cartesia

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-openai

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

pvcheetah

On-device streaming speech-to-text engine powered by deep learning

vision-agents-plugins-gemini

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-openrouter

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-smart-turn

Smart Turn detection plugin for Vision Agents

vision-agents-plugins-elevenlabs

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-ultralytics

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-kokoro

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-anthropic

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

vision-agents-plugins-fast-whisper

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.